基于筛选压缩的类Apriori算法的研究 |
| |
作者单位: | 常州机电职业技术学院信息工程系 |
| |
摘 要: | 该文根据用户的Web访问路径应用关联规则和类Apriori算法挖掘出该用户的频繁访问路径,通过对Apriori算法和目前针对提高该算法效率的各种优化技术的详细分析和研究,对类Apriori算法进行了改进,提出了基于筛选压缩的类Apriori挖掘算法,并进行了模拟实验,比较结果显示基于筛选压缩的类Apriori挖掘算法挖掘用户频繁遍历路径的效率高于类Apriori算法,最终可获取用户的频繁遍历路径。
|
关 键 词: | Web日志挖掘 频繁遍历路径 类Apriori算法 筛选压缩 |
The Research Based on the Homo-Apriori of Riddling Compression Algorithm |
| |
Authors: | ZHANG Li SHENG Yun-yao |
| |
Abstract: | Basing on the user's Web access path frequent access sequences were mined by using the association rules and homo-Apriori al-gorithm. The Apriori algorithms of association rules and all kinds of optimized techniques which were designed to promote the algorithmsefficiency were studied and discussed in detail here. Based on the basic,the homo-Apriori algorithm was improved and the homo-Apriorialgorithm of riddling compression was proposed. And hasing carried on the simulation,the result demonstrats that the frequent access se-quences mined by homo-Apriori algorithm of riddling compression is quickly than it mined by homo-Apriori. Eventually,the algorithmof users frequent access sequences is found. |
| |
Keywords: | Web log mining Frequent access sequences Homo-Apriori algorithm Riddling Compression |
本文献已被 CNKI 等数据库收录! |
|